Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
存货报废与审批核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local ledger-checking skill whose code and instructions match its stated purpose and do not show hidden network, persistence, or destructive behavior.
Install only if you are comfortable running a local Node-based checker on inventory scrap and approval ledger text. It reads the input file path you provide and reports in Chinese; it does not appear to send data over the network or make persistent system changes.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This code’s comments, prompts, errors, status notes, and sample input are all written in Chinese, and the runtime messages returned to users are also Chinese-only. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as a '合同全文' (full contract text), but the skill is specifically for checking inventory scrap and approval ledgers. This is not merely incomplete documentation: it describes a different document type than the code and manifest are supposed to handle, creating intent confusion about the accepted input domain.
- Content